The Creators of Baldur's Gate 3 Explains Its Application of Machine Learning for New Divinity
The studio behind popular RPGs like Baldur's Gate 3 and Divinity: Original Sin just teased its next major project, creating significant hype within the player base. However, recent remarks from the studio's co-founder have brought a new dimension to the narrative, focusing on the team's approach toward machine learning.
Augmenting Workflows, Not Cutting Jobs
In a recent statement, the studio's founder detailed that the company is employing machine learning for particular ancillary tasks. These involve developing PowerPoint slides, creating rough visual ideas, and creating temporary dialogue.
Notably, Vincke made clear that the final material in the game will be crafted entirely by actual creatives. "Our team is creating all the content manually," he stated.
Larian is actively increasing our team of concept artists and are currently forming narrative groups.
Given that visual development is being particularly referenced — we presently have over twenty artistic staff and have roles to fill for additional creatives.
Each initiative we do is incremental and designed to enabling creatives to spend more time on actual creation.
Any machine learning application used well is supplementary to a artist's process, not a replacement for their skill.
Responding to Feedback and Defining the Path
The revelation of employing this technology originally sparked unease among a segment of the fanbase. In reply, Vincke offered further clarification on public forums.
"At Larian, we employ these tools to explore references, similar to we use the internet and reference books," he stated. "During the very early planning process we use it as a simple sketch for structure which we then swap out with authentic concept art."
He continued, "Our studio recruits artists for their unique talent, not for their ability to follow what a AI generates."
Focused Uses for Machine Learning
Vincke had earlier outlined the studio's targeted method to machine learning, grouping its use into key pillars:
- Automation of Tedious Tasks: This includes motion capture cleaning, dialogue cleanup, and technical processes like retargeting animations.
- Fast-Tracked Experimentation: Using tools to speedily create rough versions of mechanics to experiment with concepts ahead of complete implementation.
- Long-Term Aspirations: Investigating how machine learning could one day enhance emergent reactivity, particularly in creating player-driven narratives in a detailed game universe.
He specifically affirmed that core creative disciplines — like writing — are not departments where the company is cutting artistic talent. In fact, Larian is recruiting more in these precise positions.
"Our studio is not shipping a game with any AI components, nor considering trimming down staff to swap them out with artificial intelligence," Vincke stated definitively.
